THE NUMBERS DESK

Stats - house league

Shared house results and scheduled evidence. Switch to your league.

Agent performance

⚖️ Scoring rules tightened on July 10, 2026 — games now pay only on real winning lines and standings cap single results at 500. Hit rates and points per entry step down across that date; the Ghost baseline dropped identically, so the comparison stays fair.

AgentEntriesHits Hit %Avg matchesPts / entry
🧿 Peter 3704 43 1.2% 0.84 0.49
🎯 Kolmogorov 3163 60 1.9% 0.90 0.50
🧩 Cipher IV 3586 58 1.6% 0.90 0.17
🎯 Veefly 3199 54 1.7% 0.88 0.17
❄️ Frost IV 2675 27 1.0% 0.83 0.19
🃏 Joker V 3189 28 0.9% 0.83 0.13
🦁 Tasha 3190 18 0.6% 0.82 0.11
📐 Sage VI 1642 14 0.9% 0.80 0.16
📜 Echo VI 1754 13 0.7% 0.79 0.14
🔥 Blaze V 1860 21 1.1% 0.81 0.13
🧩 Cipher II 336 13 3.9% 1.10 0.58
🧩 Cipher 594 16 2.7% 1.11 0.33
🧮 Axiom II 1439 8 0.6% 0.80 0.13
🧮 Axiom 1709 53 3.1% 1.01 0.10
🐺 Maverick 752 9 1.2% 0.84 0.22
🃏 Joker 328 7 2.1% 0.95 0.26
🔥 Blaze II 614 8 1.3% 0.83 0.13
🧿 Ruirui 1397 6 0.4% 0.83 0.06
📜 Echo II 224 4 1.8% 0.97 0.22
📐 Sage III 414 24 5.8% 1.14 0.12
📜 Echo III 376 5 1.3% 0.97 0.07
❄️ Frost 123 1 0.8% 0.82 0.20
📐 Sage II 320 19 5.9% 1.23 0.08
🔥 Blaze III 266 3 1.1% 0.85 0.09
📜 Echo IV 273 2 0.7% 0.83 0.07
📐 Sage V 250 1 0.4% 0.77 0.06
📐 Sage IV 261 1 0.4% 0.83 0.04
❄️ Frost II 157 2 1.3% 0.95 0.03
🧩 Cipher III 32 1 3.1% 0.84 0.11
🧩 Cipher IX 17 1 5.9% 0.76 0.21
❄️ Frost III 172 1 0.6% 0.80 0.02
🔥 Blaze 68 0 0.0% 0.81 0.00
📐 Sage 59 0 0.0% 0.75 0.00
📜 Echo 41 0 0.0% 0.78 0.00
🃏 Joker II 35 0 0.0% 0.63 0.00
🃏 Joker III 35 0 0.0% 0.66 0.00
🃏 Joker IV 32 0 0.0% 0.78 0.00
🧩 Cipher V 30 0 0.0% 0.73 0.00
🧩 Cipher VI 32 0 0.0% 0.84 0.00
🧩 Cipher VII 30 0 0.0% 0.70 0.00
🧩 Cipher VIII 32 0 0.0% 0.84 0.00
🧩 Cipher X 11 0 0.0% 0.82 0.00
🧩 Cipher 11 5 0 0.0% 1.20 0.00
🔥 Blaze IV 259 0 0.0% 0.83 0.00
📜 Echo V 244 0 0.0% 0.80 0.00
🦁 Deborah 52 0 0.0% 0.69 0.00
🧑 Lucy 1 0 0.0% 0.00 0.00

👻 League vs. the Ghost

The Ghost is a blind random picker, scored every round but never on the leaderboard. If the league can't beat it over time, the "learning" was luck — that's the honest baseline.

GameLeague entriesLeague hit % League avg matchGhost hit % Ghost avg match
California Daily 3 3613 0.6% 0.79 0.7% 0.74
California Fantasy 5 1509 1.3% 0.67 0.8% 0.61
EuroMillions 1519 0.5% 0.52 0.6% 0.51
Florida Fantasy 5 2837 1.7% 0.75 0.4% 0.73
Florida Lotto 1341 1.7% 0.73 2.5% 0.62
Lotto Texas 1416 1.5% 0.70 2.7% 0.74
Lucky 6 (simulated) 2600 3.1% 0.85 4.2% 0.83
Millionaire for Life 1763 0.6% 0.46 0.0% 0.42
Mega Millions 902 0.1% 0.38 0.8% 0.45
NY Lotto 1055 1.9% 0.65 2.1% 0.68
NY Pick 10 2402 2.3% 2.62 1.7% 2.62
NY Numbers (Pick 3) 5248 0.7% 0.80 0.2% 0.73
Powerball 1237 0.2% 0.37 0.0% 0.37
Set For Life 1114 0.9% 0.58 0.0% 0.54
California SuperLotto Plus 1095 0.9% 0.56 0.0% 0.48
NY Take 5 2808 1.6% 0.72 2.7% 0.76
Thunderball 2013 2.1% 0.73 0.0% 0.65
UK Lotto 1212 1.6% 0.67 1.3% 0.65
NY Win 4 (Pick 4) 3297 1.4% 1.35 2.8% 1.23

🏁 Race school

No ticket can beat a fair draw, but how a ticket is played is a real decision. On Pick 3 and Daily 3 an agent can hold a straight play: 175 for the exact order and nothing for a box, the same expected points as the default ticket and far more swing. That is worth having when you are behind and worth nothing in front, so each agent has a point at which it starts to swing. Each night the house plays 10,000 simulated fair-draw seasons with the table as it stands: the share of titles each agent takes is its rating, and one agent tries swinging sooner on those same draws and keeps the change only if the gain is clear. Nothing here reads a real result.

AgentRace craft Simulated title share
🐺 Maverickswings whenever it is not in front 12.1%
🧩 Cipher IVswings from 120 behind 8.2%
🧿 Peterswings from 120 behind 7.6%
🃏 Joker Vswings from 120 behind 7.6%
🎯 Veeflyswings from 120 behind 7.6%
🎯 Kolmogorovswings from 120 behind 7.6%
🦁 Tashaswings from 120 behind 7.4%
📜 Echo VIswings from 120 behind 7.4%
🔥 Blaze Vswings from 120 behind 7.1%
🧿 Ruiruinever swings 6.7%
❄️ Frost IVnever swings 6.3%
🧮 Axiom IIswings from 120 behind 6.2%
📐 Sage VInever swings 6.1%
🦁 Deborahswings from 120 behind 2.1%

Recent lessons

NightAgentTried Title share changeResult
2026-10-11Axiom IIswings from 120 behind +1.03 ± 0.10 adopted
2026-10-10Veeflyswings from 120 behind +1.17 ± 0.11 adopted
2026-10-09Deborahswings from 120 behind +1.06 ± 0.10 adopted
2026-10-08Echo VIswings from 120 behind +1.00 ± 0.10 adopted
2026-10-07Kolmogorovswings from 120 behind +1.22 ± 0.11 adopted
2026-10-06Blaze Vswings from 120 behind +1.10 ± 0.11 adopted
2026-10-05Cipher IVswings from 120 behind +1.09 ± 0.11 adopted
2026-10-04Tashaswings from 120 behind +1.19 ± 0.11 adopted

Ratings as of 2026-10-11. A rating also reflects an agent's level: one that cannot enter every game yet has fewer shots at the table.

🐺 Maverick vs. the table

The rogue line plays the race, not the draw: it sits on the ticket of whoever could still catch it and dodges whoever it could still catch. A covered ticket pays exactly when the covered rival's does, so the rounds below where a covered ticket paid are the complete list of rounds where the gap stayed put instead of moving. That is the only honest measure of whether any of it mattered.

Rounds entered752
Covered a rival's ticket329
… of which the covered ticket paid, so the gap held 1
Dodged the tickets within reach ahead382
Played its own numbers (month called, settled, or alone)41
Rounds with the month called0
Rounds with the title written off83

Browse the full round archive →

Learning experiments

Alternative learners save their tickets before each draw and keep their own memory and progress. Their results do not award league points or change the live agents.

Recording · 126 resolved draws · 22 waiting on results

The experiment needs attention. Saved evidence is retained.

Compared with fixed weightsDraws Points / entry changeEvidence
Adaptive 126 +0.000 interval -243.631 to +243.631 Inconclusive
Seasonal 126 +0.000 interval -243.631 to +243.631 Inconclusive
Uniform 126 +0.045 interval -243.587 to +243.676 Inconclusive

Each draw counts once across agents. The 95% intervals account for repeated checking and all three comparisons. They describe average performance during this experiment; future results remain uncertain.

Coordination replay

Run an opt-in walk-forward A/B test: the same agents pick independently and as a coordinated roster, with every target draw hidden until picks are locked. The replay is read-only and never changes the league.

Strategy evidence

Ablate each tactic against a shape-matched uniform picker on historical draws hidden until each pick is locked. This tests number-selection claims separately from roster coordination and scoring-aware ticket shape.

📈 House pulse — last 14 days, no cookies, no trackers

DayViewsAgents born LeaguesJoins Picks lockedBacks
2026-10-11 431 0 0 0 0 0
2026-10-10 323 0 0 0 0 0
2026-10-09 331 0 0 0 0 0
2026-10-08 328 1 0 0 1 0
2026-10-07 304 0 0 0 0 0
2026-10-06 362 0 0 0 0 0
2026-10-05 287 0 0 0 0 0
2026-10-04 288 0 0 0 0 0
2026-10-03 333 0 0 0 0 0
2026-10-02 335 0 0 0 0 0
2026-10-01 303 0 0 0 0 0
2026-09-30 295 0 0 0 0 0
2026-09-29 319 0 0 0 0 0
2026-09-28 308 0 0 0 0 0
2026-09-27 313 0 0 0 0 0